Due to its plug in-based design, the usage of Synapse can be very general. Synapse is based on the Microsoft .NET framework and all Synapse components are also .NET components. Although Peltarion has yet to release an official API for the Synapse platform, user made components are emerging, some of them being original, demonstrating the openness of the platform.
Features
The development cycle in Synapse is based on the canonical data mining cycle. A notable difference however is that in Synapse that cycle is not linear, but supports an iterative approach where the user can freely move between the steps. Synapse features four different operating modes that make up the development cycle.
Preprocessing
Preprocessing in Synapse
The preprocessing mode is for data mining and data preparation. In this mode the user can import, visualize, explore and transform data in a variety of ways. Data is imported through the use of format components. The standard release includes format components for reading and writing data from CSV (text) files, SQL databases, images and XML. The imported data can be visualized through visualizer components and filters can be applied to the data. The filter components range from simple data rearrangement to more advanced FFT and outlier removal filters.
The visualizers include a variety of plots and grids, which can be interconnected and branched out to perform complex data mining tasks.
Design
In design mode components are linked to construct a topology. Linked components enable a signal flow creating a pipe filter machine. When a signal is set on a component, it filters the signal in some way and the filtered signal can then be piped to the next component in the linked chain of components that form the topology. The components can be either static or adaptive. Besides regular filters, they can be sources or sinks (like plots or data loggers). The standard distribution of synapse comes with a variety of components, ranging from simple neural network components such as weight layers and function layers, to whole neural networks such as self-organizing maps and more complex static elements like for instance the fuzzy logic component. The control system is chosen and configured in design mode as well.
Training
The training mode is used for training (adapting) the system, or more generally to start the control system that regulates the information flow. It is visually similar to design mode and the same components are displayed. As the components have support for context sensitive displays, they can have a different visual appearance in training. In addition to running the control system, training mode allows the execution of high-level optimizers such as genetic algorithms, particle swarm optimization and simulated annealing. Remote execution and training is also possible in this mode.
Postprocessing
Confidence analysis in postprocessing in Synapse
The postprocessing mode is for analyzing a trained system and the preparation of such a system for end use. System performance can be tested using statistical analysis, the sensitivity of the input-output relations of a system can be analyzed (sensitivity analysis) and reports can be generated.
One of the most important postprocessing components is the deployment component.
Deployment
The deployment component allows the export of a system made in Synapse to a single .NET component. The system in the development environment is downscaled so that it only contains the minimal necessary requirements for execution and then compiled into an assembly. This assembly can then be used in any .NET framework or .NET Compact Framework application. The latter allows the deployment to embedded devices.
DeployedNeuralNetnet=newDeployedNeuralNet();// Create nn objectMatrixinput=someSensor.GetData();// Get data from some sensornet.Input_Sensor=input;// Set inputs to the nnnet.Run();// Run the nn control systemsomeMotor.Power=net.Output_Port0;// Set the power of some motor to the output of the nn
Artificial neural networks (ANNs), usually simply called neural networks (NNs) or, more simply yet, neural nets, are computing systems inspired by the biological neural networks that constitute animal brains.
A self-organizing map (SOM) or self-organizing feature map (SOFM) is an unsupervised machine learning technique used to produce a low-dimensional representation of a higher dimensional data set while preserving the topological structure of the data. For example, a data set with p variables measured in n observations could be represented as clusters of observations with similar values for the variables. These clusters then could be visualized as a two-dimensional "map" such that observations in proximal clusters have more similar values than observations in distal clusters. This can make high-dimensional data easier to visualize and analyze.
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.
Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a compact internal representation of its world and then generate imaginative content from it. In contrast to supervised learning where data is tagged by an expert, e.g. as a "ball" or "fish", unsupervised methods exhibit self-organization that captures patterns as probability densities or a combination of neural feature preferences. The other levels in the supervision spectrum are reinforcement learning where the machine is given only a numerical performance score as guidance, and semi-supervised learning where a smaller portion of the data is tagged. Two broad methods in Unsupervised Learning are Neural Networks and Probabilistic Methods.
An artificial neuron is a mathematical function conceived as a model of biological neurons, a neural network. Artificial neurons are elementary units in an artificial neural network. The artificial neuron receives one or more inputs and sums them to produce an output. Usually each input is separately weighted, and the sum is passed through a non-linear function known as an activation function or transfer function. The transfer functions usually have a sigmoid shape, but they may also take the form of other non-linear functions, piecewise linear functions, or step functions. They are also often monotonically increasing, continuous, differentiable and bounded. Non-monotonic, unbounded and oscillating activation functions with multiple zeros that outperform sigmoidal and ReLU like activation functions on many tasks have also been recently explored. The thresholding function has inspired building logic gates referred to as threshold logic; applicable to building logic circuits resembling brain processing. For example, new devices such as memristors have been extensively used to develop such logic in recent times.
Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension. Working in high-dimensional spaces can be undesirable for many reasons; raw data are often sparse as a consequence of the curse of dimensionality, and analyzing the data is usually computationally intractable. Dimensionality reduction is common in fields that deal with large numbers of observations and/or large numbers of variables, such as signal processing, speech recognition, neuroinformatics, and bioinformatics.
Intelligent control is a class of control techniques that use various artificial intelligence computing approaches like neural networks, Bayesian probability, fuzzy logic, machine learning, reinforcement learning, evolutionary computation and genetic algorithms.
Beamforming or spatial filtering is a signal processing technique used in sensor arrays for directional signal transmission or reception. This is achieved by combining elements in an antenna array in such a way that signals at particular angles experience constructive interference while others experience destructive interference. Beamforming can be used at both the transmitting and receiving ends in order to achieve spatial selectivity. The improvement compared with omnidirectional reception/transmission is known as the directivity of the array.
A neural network is a network or circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up of biological neurons, or an artificial neural network, used for solving artificial intelligence (AI) problems. The connections of the biological neuron are modeled in artificial neural networks as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed. This activity is referred to as a linear combination. Finally, an activation function controls the amplitude of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be −1 and 1.
Orange is an open-source data visualization, machine learning and data mining toolkit. It features a visual programming front-end for explorative rapid qualitative data analysis and interactive data visualization.
Neural network software is used to simulate, research, develop, and apply artificial neural networks, software concepts adapted from biological neural networks, and in some cases, a wider array of adaptive systems such as artificial intelligence and machine learning.
Computational neurogenetic modeling (CNGM) is concerned with the study and development of dynamic neuronal models for modeling brain functions with respect to genes and dynamic interactions between genes. These include neural network models and their integration with gene network models. This area brings together knowledge from various scientific disciplines, such as computer and information science, neuroscience and cognitive science, genetics and molecular biology, as well as engineering.
Spiking neural networks (SNNs) are artificial neural networks that more closely mimic natural neural networks. In addition to neuronal and synaptic state, SNNs incorporate the concept of time into their operating model. The idea is that neurons in the SNN do not transmit information at each propagation cycle, but rather transmit information only when a membrane potential – an intrinsic quality of the neuron related to its membrane electrical charge – reaches a specific value, called the threshold. When the membrane potential reaches the threshold, the neuron fires, and generates a signal that travels to other neurons which, in turn, increase or decrease their potentials in response to this signal. A neuron model that fires at the moment of threshold crossing is also called a spiking neuron model.
Data preprocessing can refer to manipulation or dropping of data before it is used in order to ensure or enhance performance, and is an important step in the data mining process. The phrase "garbage in, garbage out" is particularly applicable to data mining and machine learning projects. Data-gathering methods are often loosely controlled, resulting in out-of-range values, impossible data combinations, and missing values, etc.
Fault detection, isolation, and recovery (FDIR) is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Two approaches can be distinguished: A direct pattern recognition of sensor readings that indicate a fault and an analysis of the discrepancy between the sensor readings and expected values, derived from some model. In the latter case, it is typical that a fault is said to be detected if the discrepancy or residual goes above a certain threshold. It is then the task of fault isolation to categorize the type of fault and its location in the machinery. Fault detection and isolation (FDI) techniques can be broadly classified into two categories. These include model-based FDI and signal processing based FDI.
There are many types of artificial neural networks (ANN).
An adaptive neuro-fuzzy inference system or adaptive network-based fuzzy inference system (ANFIS) is a kind of artificial neural network that is based on Takagi–Sugeno fuzzy inference system. The technique was developed in the early 1990s. Since it integrates both neural networks and fuzzy logic principles, it has potential to capture the benefits of both in a single framework. Its inference system corresponds to a set of fuzzy IF–THEN rules that have learning capability to approximate nonlinear functions. Hence, ANFIS is considered to be a universal estimator. For using the ANFIS in a more efficient and optimal way, one can use the best parameters obtained by genetic algorithm. It has uses in intelligent situational aware energy management system.
In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.
In deep learning, a convolutional neural network is a class of artificial neural network (ANN), most commonly applied to analyze visual imagery. CNNs are also known as Shift Invariant or Space Invariant Artificial Neural Networks (SIANN), based on the shared-weight architecture of the convolution kernels or filters that slide along input features and provide translation-equivariant responses known as feature maps. Counter-intuitively, most convolutional neural networks are not invariant to translation, due to the downsampling operation they apply to the input. They have applications in image and video recognition, recommender systems, image classification, image segmentation, medical image analysis, natural language processing, brain–computer interfaces, and financial time series.
This page is based on this Wikipedia article Text is available under the CC BY-SA 4.0 license; additional terms may apply. Images, videos and audio are available under their respective licenses.
